Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0064. Min Range: -4.0064
Max Act: 4.0064. Min Act: -0.1700
Data Index: 6008087 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9751. Min Act: -0.1700
Data Index: 6725409 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9751. Min Act: -0.1700
Data Index: 1321101 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9751. Min Act: -0.1700
Data Index: 3252635 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9126. Min Act: -0.1700
Data Index: 3656943 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9126. Min Act: -0.1700
Data Index: 1321098 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.9126. Min Act: -0.1700
Data Index: 8607573 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8813. Min Act: -0.1700
Data Index: 6984720 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8813. Min Act: -0.1700
Data Index: 7072387 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5984621 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 3019463 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8813. Min Act: -0.1700
Data Index: 5787856 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 6201881 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 6281931 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 966524 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 1977952 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8501. Min Act: -0.1700
Data Index: 3697614 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8188. Min Act: -0.1700
Data Index: 3124185 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8188. Min Act: -0.1700
Data Index: 5753996 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0064. Min Range: -4.0064
Max Act: 3.8188. Min Act: -0.1700
Data Index: 2077521 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19